Search Results for author:
Found 9 papers, 1 papers with code
Fewmatch: Dynamic Prototype Refinement for Semi-Supervised Few-Shot Learning
Semi-Supervised Few-shot Learning (SS-FSL) investigates the benefit of incorporating unlabelled data in few-shot settings.
Batch Group Normalization
Among previous normalization methods, Batch Normalization (BN) performs well at medium and large batch sizes and is with good generalizability to multiple vision tasks, while its performance degrades significantly at small batch sizes.
Boosting Few-Shot Learning With Adaptive Margin Loss
Few-shot learning (FSL) has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in learning to generalize from a few examples.
Ranked #1 on
Few-Shot Image Classification
on ImageNet (1-shot)
Universal Person Re-Identification
Most state-of-the-art person re-identification (re-id) methods depend on supervised model learning with a large set of cross-view identity labelled training data.
Self-Referenced Deep Learning
Whilst being able to create stronger target networks compared to the vanilla non-teacher based learning strategy, this scheme needs to train additionally a large teacher model with expensive computational cost.
Collaborative Deep Learning Across Multiple Data Centers
Valuable training data is often owned by independent organizations and located in multiple data centers.
Person Search by Multi-Scale Matching
In contrast to previous studies, we show that sufficiently reliable person instance cropping is achievable by slightly improved state-of-the-art deep learning object detectors (e. g. Faster-RCNN), and the under-studied multi-scale matching problem in person search is a more severe barrier.
Knowledge Distillation by On-the-Fly Native Ensemble
Knowledge distillation is effective to train small and generalisable network models for meeting the low-memory and fast running requirements.
Deep Reinforcement Learning Attention Selection for Person Re-Identification
Existing person re-identification (re-id) methods assume the provision of accurately cropped person bounding boxes with minimum background noise, mostly by manually cropping.
